Abstract | ||
---|---|---|
In this paper, we address the task of utterance level emotion recognition in conversations using commonsense knowledge. We propose COSMIC, a new framework that incorporates different elements of commonsense such as mental states, events, and causal relations, and build upon them to learn interactions between interlocutors participating in a conversation. Current state-of-the-art methods often encounter difficulties in context propagation, emotion shift detection, and differentiating between related emotion classes. By learning distinct commonsense representations, COSMIC addresses these challenges and achieves new state-of-the-art results for emotion recognition on four different benchmark conversational datasets. Our code is available at https://github.com/declare-lab/conv-emotion. |
Year | DOI | Venue |
---|---|---|
2020 | 10.18653/V1/2020.FINDINGS-EMNLP.224 | EMNLP |
DocType | Volume | Citations |
Conference | 2020.findings-emnlp | 1 |
PageRank | References | Authors |
0.34 | 24 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Deepanway Ghosal | 1 | 21 | 3.46 |
Navonil Majumder | 2 | 206 | 12.78 |
Alexander Gelbukh | 3 | 2843 | 269.19 |
Rada Mihalcea | 4 | 6460 | 445.54 |
Soujanya Poria | 5 | 1336 | 60.98 |